© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40451
    Prev
    Next
    INDEX
    Explanations

    words that emphasize relationships and associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordo
    -0.06
    ateau
    -0.06
    ubber
    -0.06
    μβ
    -0.06
    orda
    -0.06
    Short
    -0.06
     Downtown
    -0.06
    ós
    -0.06
    lesc
    -0.06
    ãĤĪãģı
    -0.06
    POSITIVE LOGITS
    )prepare
    0.08
    .scalablytyped
    0.07
    ocs
    0.07
    zion
    0.07
    avs
    0.07
    åĬŁ
    0.06
    rar
    0.06
    hana
    0.06
    Unnamed
    0.06
    .djang
    0.06
    Activations Density 0.000%

    No Known Activations